search

castorini / howl

Wake word detection modeling toolkit for Firefox Voice, supporting open datasets like Speech Commands and Common Voice.
Mozilla Public License 2.0
201 stars 30 forks source link

initial version of serialize test case #82

Closed ljj7975 closed 3 years ago

ljj7975 commented 3 years ago

Outline for #56

I didn't touch anything in serialize.py except that one #TODO is added 

# TODO:: process function should also take in sample (AudioClipExample)
#        and use sample.audio_data when metadata.path does not exist

Also, I only added the following line for base.py

# TODO:: id should be an explicit variable in order to support datasets creation with the audio data in memory